mlsanityData to 7 Oct 2026

Failure Modes of LLMs for Causal Reasoning on Narratives

arXiv 2410.23884 ↗First posted 31 Oct 2024cs.LG cs.CLcited by 12

On the map: LLM reasoning → Causal reasoning in LLMs

Abstract (arXiv)

The ability to robustly identify causal relationships is essential for autonomous decision-making and adaptation to novel scenarios. However, accurately inferring causal structure requires integrating both world knowledge and abstract logical reasoning. In this work, we investigate the interaction between these two capabilities through the representative task of causal reasoning over narratives. Through controlled synthetic, semi-synthetic, and real-world experiments, we find that state-of-the-art large language models (LLMs) often rely on superficial heuristics -- for example, inferring causality from event order or recalling memorized world knowledge without attending to context. Furthermore, we show that simple reformulations of the task can elicit more robust reasoning behavior. Our evaluation spans a range of causal structures, from linear chains to complex graphs involving colliders and forks. These findings uncover systematic patterns in how LLMs perform causal reasoning and lay the groundwork for developing methods that better align LLM behavior with principled causal inference.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Placed in Causal reasoning in LLMs, one of 17 directions in LLM reasoning. Builds on 26 of its 46 references that are in the map. First posted on arXiv 31 Oct 2024.

Builds on

26 of 46 references.

Closest ancestors · 3

Same direction, newest first

  1. 2023Is ChatGPT a Good Causal Reasoner? A Comprehensive Evaluation12 May
  2. 2023COLA: Contextualized Commonsense Causal Reasoning from the Causal Inference Perspective9 May
  3. 2023Causal Reasoning and Large Language Models: Opening a New Frontier for Causality28 Apr

Other references · 23

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  2. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  3. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,203
  4. 2019HellaSwag: Can a Machine Really Finish Your Sentence?cited by 4,018
  5. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  6. 2019Language Models as Knowledge Bases?cited by 1,922
  7. 2019How Can We Know What Language Models Know?cited by 953
  8. 2024Training Language Models to Self-Correct via Reinforcement Learningcited by 405
  9. 2023Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflictscited by 333
  10. 2021Hurdles to Progress in Long-form Question Answeringcited by 166
  11. 2023Causal Parrots: Large Language Models May Talk Causality But Are Not Causalcited by 146
  12. 2023Can Large Language Models Infer Causation from Correlation?cited by 142
11 more
  1. 2024Tug-of-War Between Knowledge: Exploring and Resolving Knowledge Conflicts in Retrieval-Augmented Language Modelscited by 93
  2. 2024Alice in Wonderland: Simple Tasks Showing Complete Reasoning Breakdown in State-Of-the-Art Large Language Modelscited by 67
  3. 2023Understanding Causality with Large Language Models: Feasibility and Opportunitiescited by 53
  4. 2020Automated Storytelling via Causal, Commonsense Plot Orderingcited by 38
  5. 2021CRASS: A Novel Data Set and Benchmark to Test Counterfactual Reasoning of Large Language Modelscited by 33
  6. 2022The Causal News Corpus: Annotating Causal Relations in Event Sentences from Newscited by 24
  7. 2024Cause and Effect: Can Large Language Models Truly Understand Causality?cited by 23
  8. 2021HypoGen: Hyperbole Generation with Commonsense and Counterfactual Knowledgecited by 22
  9. 2022WikiWhy: Answering and Explaining Cause-and-Effect Questionscited by 21
  10. 2024LLMs Are Prone to Fallacies in Causal Inferencecited by 21
  11. 2022rmC small IS2: A Simplified Commonsense Inference Evaluation for Story Prosecited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 6; 2026: 6.

12 papers.

  1. 2025SagaLLM: Context Management, Validation, and Transaction Guarantees for Multi-Agent LLM Planningcited by 58
  2. 2026Large Language Model Reasoning Failurescited by 20
  3. 2025MultiHoax: A Dataset of Multi-hop False-Premise Questionscited by 8
  4. 2025Can LLMs Reconcile Knowledge Conflicts in Counterfactual Reasoningcited by 7
  5. 2025Can Large Language Models Infer Causal Relationships from Real-World Text?cited by 4
  6. 2025Automated Penetration Testing with LLM Agents and Classical Planningcited by 4
  7. 2026Student Guides Teacher: Weak-to-Strong Inference via Spectral Orthogonal Explorationcited by 3
  8. 2026LogiStory: A Logic-Aware Framework for Multi-Image Story Visualizationcited by 1
  9. 2026Why LLMs Fail at Causal Discovery and How Interventional Agents Escapecited by 1
  10. 2025Compressed Causal Reasoning: Quantization and GraphRAG Effects on Interventional and Counterfactual Accuracycited by 0
  11. 2026The Illusion of textitWhat If: Evaluating the Breakdown of Counterfactual Reasoning in LLMscited by 0
  12. 2026From Anomalies to Failures: Constructing Causal Error Graphs for Agentic Trace Diagnosiscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Unveiling Causal Reasoning in Large Language Models: Reality or Mirage?
  2. 2024A Critical Review of Causal Reasoning Benchmarks for Large Language Models
  3. 2024CausalBN-Bench: A Comprehensive Benchmark for Causal Learning Capability of LLMs
  4. 2025Causality for Natural Language Processing
  5. 2026CausalFlip: A Benchmark for LLM Causal Judgment Beyond Semantic Matching
  6. 2026Do LLMs Share Human-Like Biases? Causal Reasoning Under Prior Knowledge, Irrelevant Context, and Varying Compute Budgets
  7. 2024Language Agents Meet Causality -- Bridging LLMs and Causal World Models
  8. 2024Large Language Models and Causal Inference in Collaboration: A Survey